© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 131017
    Prev
    Next
    INDEX
    Explanations

    representation theory, sets, weight

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    os
    -1.43
     esfuer
    -1.38
    䉴
    -1.34
     essendo
    -1.32
    gação
    -1.32
     ilustración
    -1.30
    albeit
    -1.30
    籴
    -1.29
    */
    -1.29
    ,
    
    
    -1.28
    POSITIVE LOGITS
     trabajó
    1.26
     recientemente
    1.25
    </b>
    1.24
     debía
    1.20
     Curi
    1.18
     bane
    1.15
    愕
    1.14
    ⌃
    1.14
     tevens
    1.14
     detrás
    1.13
    Activations Density 0.054%

    No Known Activations